© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 17934
    Prev
    Next
    INDEX
    Explanations

    keywords related to design

    oai_token-act-pair · gpt-3.5-turbo

    references to design-related concepts and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cffffcc
    -0.91
     Thur
    -0.75
     Adin
    -0.74
    ICAN
    -0.68
     Eur
    -0.68
    SPONSORED
    -0.67
    nikov
    -0.66
    essional
    -0.66
    76561
    -0.65
    selves
    -0.64
    POSITIVE LOGITS
    ated
    0.92
    ators
    0.91
     Design
    0.90
    ation
    0.85
    Design
    0.85
    ates
    0.84
    ²¾
    0.83
    urat
    0.82
    ator
    0.81
    er
    0.81
    Activations Density 0.018%

    No Known Activations